Data Analysis and Related Applications 3

15A Dynamic Neural Network Model for Accurate Recognition of Masked Faces

Neural networks have become prominent and widely engaged in algorithmic-based machine learning networks. They are perfect in solving day-to-day issues to a certain extent. Neural networks are computing systems with several interconnected nodes. One of the numerous areas of application of neural networks is object detection. A neural network model can be adequately trained and fortified to become an object detector. Object detection techniques are used in the area of detection of face masks and recognition of masked faces in this work. This is a prominent area due to the coronavirus disease (Covid-19) pandemic and the post-pandemic phases. This pandemic has made facial biometrics the safest authentication and access control choice because other biometric means are contact-based. Experts are of the opinion that universities/colleges can only fully reopen if adequate protection and prevention means are judiciously observed.

One of these examples is wearing face masks in public places. However, wearing face masks can bring about compromises in security and safety. This necessitates the need to develop a robust and efficient model for detecting face masks on peoples’ faces for compliance checks, and recognizing the faces behind the face masks for authentication, access control and safety surveillance. There have been some breakthroughs in face mask detection and masked faces recognition using neural networks. ...